Browse skills

Evaluates question answering models using a provided dataset, generating performance metrics and identifying areas for improvement.

Generates comprehensive test plans, including edge cases and data variations, to maximize software quality coverage.

Official openai skill covering testing, data for software development workflows.

Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrappe

Optimize content performance using Sanity's best practices for A/B testing, personalization, and data-driven iteration.

Official supabase skill covering Supabase, Vitest for working with databases and data persistence.

Generate synthetic data to comprehensively test Dagster pipelines and ensure robust functionality across diverse scenarios.

Troubleshoot Ssi — provides AI agent assistance for software development workflows.

Provides testing guidance and assistance for software development workflows.

Identifies and resolves data pipeline errors within Astronomer DAGs using automated analysis and suggested fixes.

This skill analyzes tabular data to identify patterns and relationships, offering insights for data exploration and understanding.

Identifies and suggests fixes for data inconsistencies and errors within Tursodatabase datasets during testing.

Automates database schema and data integrity tests using predefined rules and edge case scenarios.

Automatically generates unit tests and converts data structures based on provided mapping specifications.

Helps with debugging, data modeling as part of software development workflows workflows.

Identifies underlying issues driving problems by analyzing data, logs, and system behavior to suggest corrective actions.

Helps with database, performance optimization, debugging as part of testing, debugging, and quality assurance workflows.

Helps with testing, data, code generation as part of testing, debugging, and quality assurance workflows.

Helps with testing, data, management as part of software development workflows workflows.

Simulates extreme user loads and data conditions to identify system vulnerabilities and performance bottlenecks.

Automates pytest test creation using common patterns like data-driven tests, fixtures, and parametrization for efficient testing.

Automates model performance evaluation against LobeHub datasets, streamlining testing workflows and ensuring consistent results.

Assess data to determine if observed results are statistically significant using various hypothesis tests.

Simulates disaster scenarios to validate data recovery plans and system resilience automatically.